2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP) 2017
DOI: 10.1109/siprocess.2017.8124512
|View full text |Cite
|
Sign up to set email alerts
|

No-reference image quality assessment through transfer learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
3
1

Relationship

1
6

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 15 publications
0
3
0
Order By: Relevance
“…However, there are few works on quality evaluation based on transfer learning. A transfer learning framework was described in [30], which learned an end-to-end image quality estimator in classification or regression. In [31], the features extracted from distorted images were transferred to the same feature space, in order to solve the problem of insufficient video contents.…”
Section: B Transfer Learning and Object Detectionmentioning
confidence: 99%
“…However, there are few works on quality evaluation based on transfer learning. A transfer learning framework was described in [30], which learned an end-to-end image quality estimator in classification or regression. In [31], the features extracted from distorted images were transferred to the same feature space, in order to solve the problem of insufficient video contents.…”
Section: B Transfer Learning and Object Detectionmentioning
confidence: 99%
“…In this study, we use a learning-based no-reference IQA algorithm DTNIQ-f by Feng et al [120] to obtain the visual quality score of distorted and adversarial images. For investigation, we collect 4966 distorted or pristine images from the traditional image quality research literature, 5000 unrecognizable fooling images from [106]; using color images from ImageNet validation set and the universal perturbation [125] method produces 49,056 recognizable adversarial images, and using gradient ascent method produces 3000 unrecognizable adversarial images.…”
Section: Methodsmentioning
confidence: 99%
“…In the meantime, studies [116][117][118][119][120][121][122][123][124][125][126][127] discover that deep neural networks can give surprisingly egregious outputs given artificially crafted fooling images or images injected with malicious changes that are hardly perceivable by the human visual system. Such Today, artificial intelligence dominates the news headlines, promises enormous potential benefits to businesses and society.…”
Section: Background and Motivationmentioning
confidence: 99%